Our daily lives bring us in contact with a rich range of materials. Human beings are remarkably good at perceiving subtle distinctions in material appearance (e.g., is this fabric silk or cotton? is this surface granite or laminate?). My group is working on understanding how humans perceive materials, and using this knowledge to drive better material modeling and recognition in graphics and vision. I will describe our recent work in modeling of cloth and translucent materials.For material recognition, we have built large-scale, crowdsourced databases of materials and objects from consumer photographs. I will describe how we use these large-scale datasets for scene understanding, intrinsic image decomposition, and material-basedimage browsing and design. This work has applications in many domains: in virtual and augmented reality, in e-commerce and retail, and inindustrial and interior design.
Kavita Bala is a Professor in the Computer Science Department at Cornell University. She received her PhD from the Massachusetts Institute of Technology (MIT), and her B. Tech. from the Indian Institute of Technology (Bombay). Bala leads research projects in material modeling and understanding, realistic rendering, perception, and computational lighting design. Her group's scalable rendering engine, Lightcuts, is thecore rendering technology in Autodesk's cloud rendering platform. Bala is the Editor-in-Chief of Transactions on Graphics (TOG), and has chaired SIGGRAPH Asia Papers (2011), co-chaired Pacific Graphics (2010) and the Eurographics Symposium on Rendering (2005). She has served as Associate Editor for TVCG and CGF. She has received the NSF CAREER award, and Cornell's College of Engineering James and Mary Tien Excellence inTeaching Award (2006 and 2009).